Yanting Zheng1, Xiaobo Chen2, Danian Li3, Yujie Liu4, Xin Tan5, Yi Liang6, Han Zhang7, Shijun Qiu8, Dinggang Shen9. 1. The First School of Clinical Medicine, Guangzhou University of Chinese Medicine, Guangzhou, Guangdong 510006, China; Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA. 2. Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA. 3. Cerebropathy Center, The First Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangdong 510405, China. 4. The First School of Clinical Medicine, Guangzhou University of Chinese Medicine, Guangzhou, Guangdong 510006, China. 5. Department of Radiology, The First Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangdong 510405, China. 6. Department of Radiology, The First Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangdong 510405, China; Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA. 7. Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA. Electronic address: hanzhang@med.unc.edu. 8. Department of Radiology, The First Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangdong 510405, China. Electronic address: qiu-sj@163.com. 9. Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA; Department of Brain and Cognitive Engineering, Korea University, Seoul 02841, Republic of Korea. Electronic address: dgshen@med.unc.edu.
Abstract
BACKGROUND: Recent functional connectivity (FC) studies have proved the potential value of resting-state functional magnetic resonance imaging (rs-fMRI) in the study of major depressive disorder (MDD); yet, the rs-fMRI-based individualized diagnosis of MDD is still challenging. METHODS: We enrolled 82 treatment-naïve first episode depression (FED) adults and 72 matched normal control (NC). A computer-aided diagnosis framework was utilized to classify the FEDs from the NCs based on the features extracted from not only traditional "low-order" FC networks (LON) based on temporal synchronization of original rs-fMRI signals, but also "high-order" FC networks (HON) that characterize more complex functional interactions via correlation of the dynamic (time-varying) FCs. We contrasted a classifier using HON feature (CHON) and compared its performance with using LON only (CLON). Finally, an integrated classification model with both features was proposed to further enhance FED classification. RESULTS: The CHON had significantly improved diagnostic accuracy compared to the CLON (82.47% vs. 67.53%). Joint classification further improved the performance (83.77%). The brain regions with potential diagnostic values mainly encompass the high-order cognitive function-related networks. Importantly, we found previously less-reported potential imaging biomarkers that involve the vermis and the crus II in the cerebellum. LIMITATIONS: We only used one imaging modality and did not examine data from different subtypes of depression. CONCLUSIONS: Depression classification could be significantly improved by using HON features that better capture the higher-level brain functional interactions. The findings suggest the importance of higher-level cerebro-cerebellar interactions in the pathophysiology of MDD.
BACKGROUND: Recent functional connectivity (FC) studies have proved the potential value of resting-state functional magnetic resonance imaging (rs-fMRI) in the study of major depressive disorder (MDD); yet, the rs-fMRI-based individualized diagnosis of MDD is still challenging. METHODS: We enrolled 82 treatment-naïve first episode depression (FED) adults and 72 matched normal control (NC). A computer-aided diagnosis framework was utilized to classify the FEDs from the NCs based on the features extracted from not only traditional "low-order" FC networks (LON) based on temporal synchronization of original rs-fMRI signals, but also "high-order" FC networks (HON) that characterize more complex functional interactions via correlation of the dynamic (time-varying) FCs. We contrasted a classifier using HON feature (CHON) and compared its performance with using LON only (CLON). Finally, an integrated classification model with both features was proposed to further enhance FED classification. RESULTS: The CHON had significantly improved diagnostic accuracy compared to the CLON (82.47% vs. 67.53%). Joint classification further improved the performance (83.77%). The brain regions with potential diagnostic values mainly encompass the high-order cognitive function-related networks. Importantly, we found previously less-reported potential imaging biomarkers that involve the vermis and the crus II in the cerebellum. LIMITATIONS: We only used one imaging modality and did not examine data from different subtypes of depression. CONCLUSIONS:Depression classification could be significantly improved by using HON features that better capture the higher-level brain functional interactions. The findings suggest the importance of higher-level cerebro-cerebellar interactions in the pathophysiology of MDD.
Authors: Ilia Nouretdinov; Sergi G Costafreda; Alexander Gammerman; Alexey Chervonenkis; Vladimir Vovk; Vladimir Vapnik; Cynthia H Y Fu Journal: Neuroimage Date: 2010-05-17 Impact factor: 6.556
Authors: J Douglas Bremner; Meena Vythilingam; Eric Vermetten; Ahsan Nazeer; Jahangir Adil; Sarfraz Khan; Lawrence H Staib; Dennis S Charney Journal: Biol Psychiatry Date: 2002-02-15 Impact factor: 13.382
Authors: Beth M Turner; Sergio Paradiso; Cherie L Marvel; Ronald Pierson; Laura L Boles Ponto; Richard D Hichwa; Robert G Robinson Journal: Neuropsychologia Date: 2006-11-22 Impact factor: 3.139
Authors: Manpreet K Singh; Shelli R Kesler; S M Hadi Hosseini; Ryan G Kelley; Debha Amatya; J Paul Hamilton; Michael C Chen; Ian H Gotlib Journal: Biol Psychiatry Date: 2013-04-18 Impact factor: 13.382
Authors: Dmitry D Bezmaternykh; Mikhail Ye Melnikov; Andrey A Savelov; Lyudmila I Kozlova; Evgeniy D Petrovskiy; Kira A Natarova; Mark B Shtark Journal: Neural Plast Date: 2021-01-15 Impact factor: 3.599